MAC: A unified framework boosting low resource automatic speech recognition
This work addresses the problem of improving speech recognition accuracy in low-resource languages for AI and language technology applications, representing a novel method rather than an incremental improvement.
The paper tackles low-resource automatic speech recognition by proposing a unified framework called meta audio concatenation (MAC), which leverages a concatenative synthesis text-to-speech system to integrate language pronunciation rules and adjust the TTS process, resulting in reductions in character error rate (CER) by over 15% across multiple languages and achieving a 10.9% CER on Cantonese with a 30% relative improvement over wav2vec2.
We propose a unified framework for low resource automatic speech recognition tasks named meta audio concatenation (MAC). It is easy to implement and can be carried out in extremely low resource environments. Mathematically, we give a clear description of MAC framework from the perspective of bayesian sampling. In this framework, we leverage a novel concatenative synthesis text-to-speech system to boost the low resource ASR task. By the concatenative synthesis text-to-speech system, we can integrate language pronunciation rules and adjust the TTS process. Furthermore, we propose a broad notion of meta audio set to meet the modeling needs of different languages and different scenes when using the system. Extensive experiments have demonstrated the great effectiveness of MAC on low resource ASR tasks. For CTC greedy search, CTC prefix, attention, and attention rescoring decode mode in Cantonese ASR task, Taiwanese ASR task, and Japanese ASR task the MAC method can reduce the CER by more than 15\%. Furthermore, in the ASR task, MAC beats wav2vec2 (with fine-tuning) on common voice datasets of Cantonese and gets really competitive results on common voice datasets of Taiwanese and Japanese. Among them, it is worth mentioning that we achieve a \textbf{10.9\%} character error rate (CER) on the common voice Cantonese ASR task, bringing about \textbf{30\%} relative improvement compared to the wav2vec2 (with fine-tuning).